Skip to main content
Financial Innovation

Table 2 Parameters of ARMA-GARCH models

From: The time-varying causal relationship between the Bitcoin market and internet attention

Variable

dlog_GSVI

AGSVI

returns

dlog_volume

c

− 0.001

(0.002)

0.007

(0.031)

0.130*

(0.070)

0.003

(0.002)

ar(1)

0.604***

(0.048)

0.911***

(0.012)

− 0.210

(1.862)

0.428***

(0.032)

ma(1)

− 0.792***

(0.035)

0.011

(0.038)

0.208

(1.863)

− 0.857***

(0.017)

ω

0.009***

(0.001)

0.008***

(0.001)

0.532***

(0.109)

0.082**

(0.032)

α

0.302***

(0.041)

0.274***

(0.038)

0.123***

(0.017)

0.120***

(0.031)

β

0.268***

(0.073)

0.328***

(0.066)

0.851***

(0.019)

0.374*

(0.212)

AIC

2394.657

2336.657

− 10,220.110

− 1899.097

  1. ***, **, * denote statistical significance at a 1%, 5%, and 10% level respectively. dlog_GSVI represents the first difference of logarithm of Google search volume index; AGSVI is abnormal Google search volume index; returns is Bitoin returns in logarithm; and dlog_volume is the first difference of logarithm of Bitcoin trading volume. Standard errors are reported in parentheses
Back to article page